© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 39866
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undergrad
    -0.06
     undergraduate
    -0.06
    licht
    -0.06
    erti
    -0.06
    óng
    -0.06
     lion
    -0.05
    roller
    -0.05
    agle
    -0.05
    meric
    -0.05
    .googleapis
    -0.05
    POSITIVE LOGITS
    noho
    0.09
    length
    0.08
     offered
    0.07
     vitae
    0.07
    ɵ
    0.07
     lengths
    0.07
     côt
    0.07
    ÑĢеб
    0.07
     offering
    0.07
     ofrec
    0.07
    Activations Density 0.015%

    No Known Activations